A new energy vehicle battery thermal management method and system based on big data

Abstract

The application provides a new energy automobile battery thermal management method and system based on big data, which comprises the following steps: collecting real-time data flow and historical temperature change curve in the battery pack through a distributed sensor array in real time; inputting a pre-trained time series prediction model, outputting a predicted temperature change curve and calculating a real-time temperature rising slope; obtaining an environmental comprehensive compensation amount according to the environmental temperature and the battery health state, subtracting the environmental comprehensive compensation amount from the basic safety threshold to obtain a dynamic safety threshold; determining a dynamic temperature compensation amount through a preset slope grading mechanism, subtracting the dynamic temperature compensation amount from the dynamic safety threshold to obtain an early intervention temperature point; when the battery pack temperature reaches the early intervention temperature point, starting a hierarchical cooling system, and dynamically switching the cooling power level according to the growth interval of the real-time temperature rising slope. The application realizes precise control of the battery temperature and significantly reduces energy consumption.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a new energy vehicle battery thermal management method and system based on big data. BACKGROUND

[0002] With the rapid development of new energy vehicle industry, as the core energy storage component, the thermal safety management of battery is directly related to the vehicle range, battery life and driving safety. Under high temperature environment or high rate charging and discharging conditions, irreversible side reaction chain reaction will be triggered in the battery, including accelerated decomposition of solid electrolyte interface film, electrolyte oxidation and positive material lattice collapse. These reactions not only cause the battery capacity to drop and internal resistance to increase, but also may trigger thermal runaway and cause safety accidents. Especially in the summer in southern China, desert areas and fast charging scenarios, battery pack temperature management faces severe challenges, and a more intelligent thermal management mechanism is urgently needed to cope with complex conditions.

[0003] The current mainstream battery thermal management system generally uses a fixed temperature threshold to trigger the cooling strategy. When the battery temperature reaches the preset threshold (usually 45-50℃), the cooling device is started. This responsive mechanism has the following defects: first, due to the thermal inertia of the battery and the delay of the cooling system, the temperature will continue to rise for several minutes after reaching the threshold, causing the battery to be exposed to high temperature environment above the safety threshold for a long time, causing irreversible electrochemical damage; second, the fixed threshold does not consider the influence of dynamic factors such as environmental temperature, battery aging degree and driving load. For example, in an environment of 40℃, the actual safety threshold needs to be lowered to below 42℃, but the existing system cannot adaptively adjust, resulting in protection failure; third, the cooling strategy is single, and full load refrigeration is used regardless of the temperature rise rate, resulting in low energy efficiency. SUMMARY

[0004] In order to solve the problems in the prior art, the present application provides a new energy vehicle battery thermal management method and system based on big data, which solves the irreversible damage problem of new energy vehicle battery caused by fixed temperature threshold triggering lag under high temperature environment, realizes accurate control of battery temperature and significantly reduces energy consumption.

[0005] In the first aspect, the present application provides a new energy vehicle battery thermal management method based on big data, comprising:

[0006] The temperature distribution data of each single battery cell in the battery pack, the charging and discharging current and voltage data, the environmental temperature and humidity data and the vehicle driving condition data are collected in real time by a distributed sensor array to obtain a real-time data stream. Based on the current spatiotemporal characteristic parameters, the historical temperature change curve under similar scenarios is retrieved from the cloud historical database.

[0007] input the real-time data stream and the historical temperature change curve into a pre-trained time series prediction model, output a predicted temperature change curve within a future set time window through multi-source data fusion processing, and calculate a real-time temperature rise slope based on the predicted temperature change curve;

[0008] According to the negative compensation effect of the ambient temperature on the basic safety threshold and the nonlinear attenuation effect of the battery health state on the basic safety threshold, an environmental comprehensive compensation quantity is obtained, the environmental comprehensive compensation quantity monotonically increases with the increase of the ambient temperature and accelerates the growth with the aggravation of the battery aging degree, the basic safety threshold is subtracted by the environmental comprehensive compensation quantity, and a dynamic safety threshold is obtained;

[0009] Based on the real-time temperature rise slope, a dynamic temperature compensation quantity is determined through a preset slope grading mechanism, the dynamic temperature compensation quantity increases in steps with the increase of the slope, and the dynamic safety threshold is subtracted by the dynamic temperature compensation quantity to obtain an early intervention temperature point.

[0010] When the battery pack temperature reaches the early intervention temperature point, the hierarchical cooling system is started, and the cooling power level is dynamically switched according to the growth interval of the real-time temperature rise slope, wherein the cooling intensity is positively correlated with the slope.

[0011] In the second aspect, the application also provides a new energy vehicle battery thermal management system based on big data, which is applied to the new energy vehicle battery thermal management method based on big data in the first aspect; the new energy vehicle battery thermal management system based on big data comprises:

[0012] The data acquisition and retrieval module acquires the temperature distribution data of each single battery cell in the battery pack, the charging and discharging current and voltage data, the environmental temperature and humidity data, and the vehicle driving condition data in real time through a distributed sensor array, obtains a real-time data stream, and retrieves a historical temperature change curve under a similar scene from a cloud historical database based on current spatiotemporal characteristic parameters.

[0013] The temperature prediction and slope generation module inputs the real-time data stream and the historical temperature change curve into a pre-trained time series prediction model, outputs a predicted temperature change curve within a future set time window through multi-source data fusion processing, and calculates a real-time temperature rise slope based on the predicted temperature change curve;

[0014] The dynamic safety threshold generation module obtains an environmental comprehensive compensation quantity according to the negative compensation effect of the ambient temperature on the basic safety threshold and the nonlinear attenuation effect of the battery health state on the basic safety threshold, the environmental comprehensive compensation quantity monotonically increases with the increase of the ambient temperature and accelerates the growth with the aggravation of the battery aging degree, the basic safety threshold is subtracted by the environmental comprehensive compensation quantity, and a dynamic safety threshold is obtained.

[0015] The early intervention point decision module determines a dynamic temperature compensation amount through a preset slope grading mechanism based on the real-time temperature rising slope, the dynamic temperature compensation amount is increased step by step with the increase of the slope, the dynamic safety threshold is subtracted by the dynamic temperature compensation amount, and an early intervention temperature point is obtained;

[0016] The staged cooling execution module starts the staged cooling system when the battery pack temperature reaches the early intervention temperature point, and dynamically switches the cooling power level according to the growth interval of the real-time temperature rising slope, wherein the cooling intensity is positively correlated with the slope.

[0017] The new energy vehicle battery thermal management method based on big data provided by the embodiment of the application can accurately generate a future temperature change curve and a dynamic safety threshold by collecting environmental parameters, driving conditions and battery state data in real time, training a time series prediction model in combination with a historical database, calculating an early intervention temperature point based on the real-time slope of the prediction curve, starting staged cooling before the temperature reaches the safety threshold, eliminating temperature overshoot, and dynamically adjusting the cooling intensity according to the slope change, thereby significantly reducing energy consumption on the premise that the battery temperature is always lower than the dynamic threshold. The scheme realizes a technical leap from 'passive response' to 'active prevention', and achieves a breakthrough in high-temperature environment adaptability, battery life protection and energy utilization efficiency in three dimensions. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a flowchart of a new energy vehicle battery thermal management method based on big data provided by the embodiment of the application;

[0019] Figure 2 is a structural schematic diagram of a new energy vehicle battery thermal management method based on big data provided by the embodiment of the application. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application.

[0021] In the description of the application, the terms 'first' and'second' are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as 'first' and'second' can explicitly or implicitly include one or more features. In the description of the application, the meaning of 'a plurality of' is two or more, unless otherwise specifically limited.

[0022] In the description of the present application, the term "for example" is used to mean "serving as an instance, example or illustration". Any embodiment described as "for example" in the present application is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the present application. In the following description, for the purpose of explanation, details are set forth. It is apparent to those skilled in the art that the present application can be practiced without the use of these specific details. In other instances, well-known structures and processes are not elaborated in order not to obscure the description of the present application with unnecessary details. Thus, the present application is not intended to be limited by the embodiments shown, but is to be accorded with the widest scope consistent with the principles and features disclosed.

[0023] Reference Figure 1 , Figure 1 is a flowchart of a new energy vehicle battery thermal management method based on big data provided by the present application, a new energy vehicle battery thermal management method based on big data, comprising:

[0024] Step 10, real-time acquisition of temperature distribution data of each single battery cell in the battery pack, charging and discharging current and voltage data, environmental temperature and humidity data and vehicle driving condition data by a distributed sensor array, obtaining a real-time data stream, based on current spatiotemporal characteristic parameters, retrieving a historical temperature change curve under a similar scene from a cloud historical database;

[0025] Step 20, inputting the real-time data stream and the historical temperature change curve into a pre-trained time series prediction model, outputting a predicted temperature change curve within a future set time window through multi-source data fusion processing, and calculating a real-time temperature rising slope based on the predicted temperature change curve;

[0026] Step 30, obtaining an environmental comprehensive compensation amount according to the negative compensation effect of environmental temperature on the basic safety threshold and the nonlinear attenuation effect of battery health state on the basic safety threshold, the environmental comprehensive compensation amount monotonically increasing with the increase of environmental temperature, and accelerating growth with the aggravation of battery aging degree, subtracting the environmental comprehensive compensation amount from the basic safety threshold to obtain a dynamic safety threshold;

[0027] Step 40, determining a dynamic temperature compensation amount through a pre-set slope grading mechanism based on the real-time temperature rising slope, the dynamic temperature compensation amount increasing in steps with the increase of the slope, and subtracting the dynamic temperature compensation amount from the dynamic safety threshold to obtain an early intervention temperature point;

[0028] Step 50, when the battery pack temperature reaches the early intervention temperature point, starting a hierarchical cooling system, and dynamically switching the cooling power level according to the growth interval of the real-time temperature rising slope, wherein the cooling intensity is positively correlated with the slope.

[0029] Specifically, in step 10, data acquisition and historical retrieval are realized by a distributed multi-source sensing network, which includes:

[0030] At least three groups of temperature sensor arrays are deployed inside the battery pack, each group containing K-type thermocouples arranged in the battery module gap and thin film temperature sensors attached to the surface of the single cell, to collect temperature distribution data at a sampling rate of 10 Hz;

[0031] A closed-loop Hall current sensor and a high-precision voltage acquisition circuit are installed in the charging and discharging circuit to synchronously obtain current and voltage waveforms at a frequency of 1 kHz;

[0032] A multi-in-one environmental monitoring unit is integrated on the roof to obtain real-time environmental temperature, humidity, air pressure and light intensity data;

[0033] Through the vehicle CAN bus interface, broadcast messages of vehicle speed, battery state of health (SOH) and state of charge (SOC) are read at a period of 500 ms;

[0034] When the vehicle starts, the historical retrieval mechanism is automatically triggered, combining the current timestamp, GPS geographic coordinates and environmental parameters into a 128-dimensional feature vector, which is uploaded to the cloud historical database through the Internet of Vehicles module, and the improved Euclidean distance algorithm is used to match similar scenarios, returning the top three historical temperature change curve original data with the highest matching degree.

[0035] In one specific embodiment, the step 10 process is executed when a certain electric vehicle is driving on a highway in the summer afternoon:

[0036] The temperature sensor array detects that the middle module temperature of the battery pack is 42.3°C, and the edge module is 38.7°C, generating a temperature distribution thermal map;

[0037] The current sensor captures a continuous discharge current of 150A, and the voltage fluctuation range is 350-365V;

[0038] The roof environmental unit measures the external air temperature of 38°C and humidity of 65%;

[0039] The CAN bus analysis shows that the vehicle speed is 110 km / h, SOH=88%, and SOC=45%;

[0040] The system automatically constructs a feature vector and uploads it to the cloud through the 5G network;

[0041] The cloud database retrieved data from the same period and road segment from 2020 to 2025 and matched three similar curves: ① a historical curve with an ambient temperature of 37℃ at the same vehicle speed on July 12, 2024; ② a curve for climbing conditions with the same SOC on August 3, 2023; and ③ an extreme temperature curve for historical high temperature warning dates. The original time-temperature data streams of the three curves were downloaded to the vehicle cache.

[0042] In the specific implementation process, in addition to data collection and retrieval, the following points should also be noted:

[0043] Temperature sensors undergo zero-point calibration every quarter, and current sensors employ dynamic calibration compensation to ensure that data errors are less than industry standard tolerances.

[0044] When GPS signal is lost, switch to base station positioning and inertial navigation fusion mode. When environmental parameters are abnormal, activate vehicle-mounted weather radar to supplement data and ensure data integrity.

[0045] In the historical data filtering rules, historical curves with differences in battery health status greater than 15% or deviations in charge / discharge rate exceeding 0.5C are excluded, and data of the same model battery pack are selected first.

[0046] Set up a safety redundancy mechanism. If cloud communication is interrupted, call up the historical data of the most recent 30 days stored locally. When there are fewer than two available data points, use the simulation curve based on the electrochemical model as a substitute.

[0047] To protect privacy, geolocation information is rasterized and blurred before transmission, reducing accuracy to 1km. 1km grid, timestamps blurred to 30-minute intervals.

[0048] Specifically, in step 20, temperature prediction and slope calculation are achieved through an embedded LSTM model, and the real-time data stream output from step 10 is combined with three historical temperature curves. , , Input to a pre-trained multi-head attention LSTM network; real-time data stream includes a temperature distribution matrix. Current ,Voltage Ambient temperature Speed ;in

[0049] The first similar scene temperature-time curve (such as the temperature change curve over time for the scene of "high-speed driving in the summer afternoon").

[0050] The second similar scene temperature-time curve (and) Scenario type consistency, slight differences in collection time or working conditions

[0051] Third similar scenario temperature-time curve (to improve data fusion redundancy and prediction accuracy)

[0052] I Battery charge and discharge current (unit: A, positive for charging, negative for discharging, reflecting battery energy flow intensity)

[0053] V: Battery voltage (unit: V, reflecting the current state of charge and health status of the battery)

[0054] Ambient temperature (unit: ℃, a key external parameter affecting battery heat dissipation efficiency, used for dynamic threshold environmental compensation calculation)

[0055] The model normalizes the input data to a 12-dimensional feature vector through the feature fusion layer where is the average temperature of the battery pack, is the temperature standard deviation, is the deviation of the historical curve and the current temperature; LSTM units are calculated by time steps, including:

[0056] Forget gate:

[0057] Generate a value between 0 and 1 to determine the proportion of historical information retained (for example, when the ambient temperature changes suddenly, reduce the weight of the historical temperature rise trend)

[0058] Input gate:

[0059] Control the degree of adoption of new input information (such as sudden large current discharge to increase the weight of current data)

[0060] Candidate state:

[0061] Generate the potential state of the current time, representing short-term thermal dynamic characteristics (such as the acceleration of instantaneous temperature rise)

[0062] Cell state update:

[0063] Fuse long-term regularity and short-term characteristics to form updated knowledge memory (for example, combine battery aging baseline and new working condition temperature rise mode)

[0064] Output gate:

[0065] Filtering the current required output information (such as the effective temperature rise signal after filtering sensor noise);

[0066] Hidden layer output:

[0067] Generate the final prediction basis, pass to the next time step or full connection layer output temperature prediction value;

[0068] In the formula

[0069] : The hidden state of the previous time step, carrying the evolution law of the historical temperature sequence (such as the temperature rise trend of the battery in the previous minute);

[0070] : The feature vector of the input time series prediction model at time t (the core parameter set integrating real-time data and scenario-based historical data);

[0071] : The cell state of the previous time step, as a long-term memory carrier to store the essential law of battery thermal characteristics (such as the heat capacity characteristics of battery materials);

[0072] : Respectively represent the weight matrix of the forget gate, input gate, candidate state, and output gate, which is obtained by training and learning, and is used to extract the contribution weight of different input features (such as the influence coefficient of current on temperature rise);

[0073] : The bias vector corresponding to the above gate, used to adjust the threshold value of the activation function and enhance the model fitting ability;

[0074] : Sigmoid activation function, compressing the input to the interval (0, 1) to realize the gating effect;

[0075] : Hyperbolic tangent activation function, normalizing the input to the interval (-1, 1) to stabilize the gradient flow;

[0076] : Hadamard product (element-wise multiplication), used for local modulation of the gating signal and state vector;

[0077] T : Battery pack average temperature (unit: ℃, reflecting the overall temperature level of the battery pack);

[0078] : Temperature standard deviation (unit: ℃, reflecting the temperature dispersion of each monomer in the battery pack, used to identify local temperature difference);

[0079] S: Vehicle speed (unit: km / h, reflects the vehicle driving condition, directly related to battery discharge power and heat production);

[0080] : First historical curve Deviation from current temperature (unit: ℃, used to correct the prediction deviation of real-time data);

[0081] : Second historical curve Deviation from current temperature (unit: ℃, same as , improves redundancy);

[0082] : Third historical curve Deviation from current temperature (unit: ℃, same as , improves redundancy);

[0083] Finally, output the temperature sequence of the next 10 minutes through the full connection layer , and calculate the real-time slope by first-order difference The model iteratively updates the prediction result at a frequency of 5Hz on the vehicle-mounted GPU.

[0084] In a specific embodiment, the step 20 process is executed with an electric SUV climbing at a speed of 100km / h at an ambient temperature of 40℃. The input data includes:

[0085] Temperature distribution matrix (center module 46.2℃ / edge module 41.3℃); discharge current 182A; voltage fluctuation 352-367V; three historical curves (2022 same section curve , same model high temperature curve , SOH=85% aging curve );

[0086] Feature vector .

[0087] The LSTM network calculation process is:

[0088] Time step : Forget gate Retains 87% of historical state;

[0089] Candidate state Calculates temperature rise trend index +0.35;

[0090] Output gate Generates the first prediction point ;

[0091] After 120 iterations (10-minute window), the prediction curve is output: peak at 3 minutes, 47.8℃, and drops to 45.2℃ at 8 minutes, the slope calculation module detects a high-growth interval flag is triggered.

[0092] In the implementation process, the following points need to be noted:

[0093] Model lightweight constraints are performed: LSTM hidden layer dimension ≤ 128, and floating-point operation amount < 15G FLOPS, meeting the vehicle chip computing power limit;

[0094] Real-time guarantee is performed: single prediction period ≤ 200ms, and if it exceeds, cached data is used and an alarm is triggered;

[0095] Confidence check is performed: when the extreme point of the prediction curve deviates from the current temperature by 30% of the battery safety tolerance, a degradation strategy is started, which includes: If

[0096] , a weighted average is used ; If

[0097] , switch to the electrochemical model .

[0098] Slope filtering is performed: Kalman filtering is applied to the original slope , where the process noise covariance , and the observation noise covariance R = 0.1 to prevent slope mutation.

[0099] Where:

[0100] : represents the filtered slope estimate at the current time, which is the true temperature rise rate after noise suppression, used for cooling strategy decision-making;

[0101] : represents the filtered slope estimate at the previous time, which is a smoothed record of historical temperature rise trend, reflecting the continuous influence of battery thermal inertia;

[0102] : represents the original slope observation value at the current time, which is the instantaneous slope obtained by fitting the prediction temperature curve using the least squares method;

[0103] : state transition matrix (scalar form), representing the time correlation coefficient of the slope, reflecting the inertia degree of the temperature rise trend; ​​​

[0104] : Kalman gain (scalar form), representing the trust weight of the observation, balancing the contribution proportion of historical estimation and current observation.

[0105] Specifically, in step 30, the dynamic safety threshold is generated by a three-stage linkage mechanism, specifically divided into steps 301, ambient temperature compensation amount calculation; step 302, battery aging compensation amount calculation; step 303, dynamic safety threshold synthesis.

[0106] Further, the step 301 collects the ambient temperature in real time through a high-precision environment sensor (collecting rate ), and inputs the into a segmented linear compensation engine to perform a three-stage judgment, which includes:

[0107] Performing a reference temperature judgment, calling the optimal working temperature median (e.g. NMC battery 25℃) in the battery material database, when , judging that the temperature has no thermal risk, and outputting the ambient temperature compensation amount ;

[0108] Performing a regular temperature rise compensation judgment, when entering the first high temperature interval ), based on the unit temperature rise side reaction acceleration rate (0.6-0.8℃ / ℃ calibrated by isothermal calorimeter), calculating , where is the material characteristic coefficient;

[0109] Performing a high-temperature strengthening compensation judgment, when (side reaction mutation point, e.g. 40℃) enters the second high temperature interval, according to the exponential growth characteristics in the Arrhenius equation , using a strengthening factor , calculating .

[0110] The step 302 obtains the state of health SOH (update period ≤24h) through the BMS, inputs the SOH into a double-threshold attenuation model to perform a hierarchical operation, including:

[0111] When SOH≥ (capacity first accelerated decay critical point, e.g. 90%) the battery health state is higher than the first health threshold, judging that the battery is in a safe life cycle, belonging to the health state partition, outputting the battery aging compensation amount ;

[0112] When When the battery health status drops to between the first and second health thresholds (e.g., 80% ≤ SOH < 90%), the battery is considered to be in the linear degradation zone. Linear compensation is then calculated based on the heat generation increase per percentage of capacity decay (calibrated to 0.3–0.5 W / %) through accelerated aging experiments. ,in This refers to the aging sensitivity coefficient.

[0113] When SOH When the thermal stability collapse threshold (e.g., 80%) is reached, the battery health status falls below the second health threshold, indicating that the battery is in the exponential decay zone. This is based on the activation energy of the reaction measured by an aging battery adiabatic calorimeter (ARC). Fit index parameter ,calculate ,in This is the baseline attenuation.

[0114] The step 303 involves the... , , The input synthesis engine performs four steps: bidirectional compensation calculation, boundary constraint, data credibility verification, and real-time early warning.

[0115] in Ambient temperature compensation (unit: °C, based on) Calculations show that the higher the ambient temperature, the greater the compensation amount, which is used to lower the dynamic safety threshold.

[0116] Battery aging compensation amount (unit: ℃, calculated based on the battery health state SOH; the lower the SOH, the more exponentially the compensation amount increases, used to adapt to the decreased thermal stability of aging batteries).

[0117] Dynamic safety threshold (unit: ℃, core control threshold, calculation formula is as follows) (Dynamically adjusted according to environment and battery status).

[0118] Basic safety threshold (unit: ℃, the upper limit of safe temperature under brand new battery condition and standard ambient temperature (25℃), which is a fixed value, such as 52℃).

[0119] Specifically, the bidirectional compensation operation is to perform an arithmetic superposition of dynamic security thresholds. Apply boundary constraints; if the result is lower than the system's allowable lower limit... (Electrolyte freezing point +10℃ safety margin), forced output Perform data credibility verification; when the environment or aging data source is abnormal, switch to historical average safety mode (call the average threshold of the same scenario in the past 30 days); provide real-time alerts when the total compensation amount... At that time, the vehicle system's high-temperature aging risk warning will be activated.

[0120] By generating dynamic safety thresholds through a three-level linkage mechanism, the corrosive effect of ambient temperature rise on battery thermal stability is quantified, solving the problem of fixed threshold protection failure under high-temperature conditions; capturing nonlinear thermal risks caused by battery aging, solving the defect of insufficient protection for aging batteries by fixed thresholds; and establishing a dynamic safety boundary driven by both environmental and aging factors to achieve intrinsic protection of battery thermal safety.

[0121] In a specific embodiment, step 30 is performed as an example of an electric vehicle operating under high load in a tropical rainforest region.

[0122] During the environmental compensation implementation process in step 301, the ambient temperature is collected in real time through the roof-mounted environmental monitoring unit. =43.5℃ (moving average per minute), synchronously calling the reference temperature from the system parameter library. =25℃ (optimal average operating temperature of NMC811 battery), high temperature critical point =40℃ (DSC determination of side reaction mutation point), conventional compensation coefficient =0.65 (calibration basis: side reaction rate increment of 1.8 times / ℃ in the 35-40℃ temperature rise zone); because 43.5℃>40℃ triggers the high-temperature enhancement compensation mode, the enhancement factor is activated. =1.75 (according to the Arrhenius equation) Calculate the activation energy. =85kJ / mol, gas constant); calculate the ambient temperature compensation amount using the enhanced compensation formula. .

[0123] During the aging compensation implementation in step 302, the health status SOH = 77% (calculated based on the capacity decay model) is obtained through the BMS, and the health threshold in the parameter library is called. =90% (capacity retention inflection point after 500 cycles) =80% (ARC test heat generation rate mutation point), baseline decay =2.3 (fitted from aging battery runaway experiment), exponential parameter =0.55 (calculated based on the enthalpy change of the SEI membrane regeneration reaction) (After normalization); because SOH=77%<80%, the degradation zone is determined, and the battery is determined to be in the exponential degradation zone; the battery aging compensation is calculated by applying the exponential formula. .

[0124] During the dynamic synthesis process in step 303, the basic safety thresholds in the electrochemical database are invoked. =52℃ (NMC811 initial heat dissipation temperature 62℃ minus 10℃ safety margin), receive the output of step 301. and the output of step 302 =11.98℃; Perform bidirectional compensation calculation, execute the synthesis formula, and calculate the dynamic safety threshold. Boundary constraints were applied because the synthesized result of 18.98℃ was higher than the system's lower limit. It directly outputs the final threshold; it provides risk warnings and environmental compensation amounts. Activate the red high-temperature aging warning icon on the vehicle's dashboard.

[0125] In the specific implementation process, attention should also be paid to parameter calibration standards, the establishment of real-time assurance mechanisms, and fault-tolerant design.

[0126] The parameter calibration specifications include The abrupt change point of the side reaction rate must be determined by differential scanning calorimetry (DSC), with an error tolerance. 1.5℃; The enthalpy change of the SEI film regeneration reaction needs to be measured in situ using a three-electrode system. Fit, satisfy (R is the gas constant); The setting must be at least 10°C higher than the freezing point of the electrolyte and verified by low-temperature differential thermal analysis (DTA).

[0127] The established real-time guarantee mechanism includes synchronizing environmental compensation cycles with temperature sampling (≤1 second), and binding aging compensation to BMS health report events; when When the temperature fluctuation per minute exceeds 5°C, activate the sliding window filter. (N adjusts itself based on climate type).

[0128] The fault-tolerant design includes switching to V2X vehicle-road cooperative meteorological data when environmental sensors fail; using an open-circuit voltage (OCV)-capacity mapping model to estimate when SOH is abnormal; and requiring cross-validation by a three-mode redundancy processor to output the majority voting result.

[0129] Specifically, in step 40, an early intervention temperature point is generated through a fourth-order decision chain, which is divided into steps 401, real-time slope extraction; step 402, slope interval determination; step 403, dynamic compensation amount generation; and step 404, intervention point synthesis.

[0130] Furthermore, step 401 involves receiving the predicted temperature change curve within a future time window via a temperature prediction module. The predicted temperature change curve is input into the sliding window analysis engine for window truncation, linear fitting, and dynamic optimization.

[0131] The window is captured at the current time. Starting from the beginning, extract a fixed duration. curve segment ( (Based on the battery thermal time constant setting)

[0132] The linear fitting uses the least squares method to fit the temperature-time relationship within the window. Output the real-time temperature rise slope ;

[0133] The dynamic optimization involves automatically expanding the window to 1.5 when the prediction confidence level p < 0.9. Improve the stability of the fit.

[0134] In step 402, the real-time temperature rise slope k is input into a three-level classifier to perform interval mapping.

[0135] when Activate low-growth intervals ( (Based on the first abrupt change point of the side reaction rate of battery materials)

[0136] when Time-activated growth interval ( (Calibrated based on the rate of temperature rise at the onset of electrolyte boiling).

[0137] when Activate the high-growth zone in a timely manner;

[0138] in

[0139] Real-time temperature rise slope (unit: ℃ / min, reflecting the rate at which the battery temperature rises, and is the core basis for graded compensation and cooling control).

[0140] Critical slope in the low / medium growth range (unit: °C / min, determined based on the first abrupt change in the side reaction rate of the battery material, e.g., 1 °C / min, slope). (In the low growth range).

[0141] Critical slope in the medium / high growth range (unit: °C / min, calibrated based on the temperature rise rate at the electrolyte boiling point, e.g., 2 °C / min, slope). (for high growth range)

[0142] Dynamic temperature compensation (unit: °C, based on) The growth range is determined; the steeper the slope, the greater the compensation amount, used to calculate the early intervention temperature point and reserve a safety margin.

[0143] The , The inflection point of reaction kinetics was determined by differential scanning calorimetry (DSC).

[0144] Step 403 calls the compensation mapping rule based on the interval determination result, and outputs when it is in a low growth interval. When in the medium growth range, output When output is in a high-growth range ; Calculate the rate of change of slope within the window ,when Time (vehicle rapid acceleration threshold), plus buffer compensation amount Final compensation amount .

[0145] Step 404 receives the dynamic security threshold. and compensation amount Execute the imposed constraints And apply constraints ( (for system protection margin).

[0146] In one specific embodiment, step 40 is executed as an example of an electric vehicle overtaking at high speed.

[0147] In step 401, during the real-time slope extraction process, the predicted curve and the temperature sequence for the next 5 minutes are input. (Time step 1 minute); Configure the sliding window settings. =3min (capturing three points: 38.9, 41.5, and 44.8℃); perform least squares fitting and solve the equation. We get k = 2.97℃ / min.

[0148] Step 402, slope interval determination, involves calling calibration parameters. ℃ / min (transition point of side reaction in graphite negative electrode) =2.0℃ / min (Electrolyte boiling point); because k=2.97> The assessment results indicate that the economy has entered a high-growth phase.

[0149] Step 403, during the dynamic compensation generation process, involves basic compensation and the activation of high-growth intervals. =8℃; Perform acceleration detection and calculate the slope change of the preceding window. Perform buffer stacking and activate. ℃, to obtain ℃.

[0150] Step 404 intervenes in the synthesis implementation process, input dynamic security threshold , calculation , the result is higher than , boundary check, direct output.

[0151] In the specific implementation process, attention should also be paid to the slope calculation robustness guarantee, interval boundary specification, compensation amount dynamic adjustment mechanism and fault tolerance design.

[0152] The slope calculation robustness guarantee includes:

[0153] Window adaptation is performed, when the prediction curve confidence p < 0.85, the window length is dynamically expanded according to ;

[0154] Outliers are filtered by using Tukey rule (when removed, IQR is the interquartile range), and outliers are removed; Fitting verification is performed, requiring linear regression determination coefficient

[0155] , otherwise switch to polynomial fitting.

[0156] The interval boundary specification includes:

[0157] The activation energy of the negative electrode SEI film decomposition reaction is determined by cyclic voltammetry (CV) , calculation (R gas constant, T temperature) for specification;

[0158] According to the temperature rise rate of the 5% weight loss point of the electrolyte thermal gravimetric analysis (TGA), the error tolerance is 0.2 ℃ / min, for specification;

[0159] The effectiveness of the boundary value is rechecked on the real vehicle platform every quarter to perform online calibration.

[0160] The compensation amount dynamic adjustment mechanism includes:

[0161] , , The initial value is set according to the battery thermal runaway time constant, and the basic compensation is adaptively adjusted according to the formula during operation (learning rate , recent prediction error mean) ;

[0162] Buffer compensation is performed, ​Positive correlation with acceleration absolute value, meet ;

[0163] Synthesis constraints, total compensation not more than 40% of the dynamic safety threshold.

[0164] The fault-tolerant design includes:

[0165] Predictive failure degradation, when the continuous 3 times fitting Switch to the simplified model based on current integral ( Battery internal resistance coefficient);

[0166] If Boundary protection, forced to promote to And limit power operation;

[0167] Storage slope k, acceleration , compensation And other key parameters, save period 10 years of safety audit.

[0168] Specifically, in step 50, the hierarchical cooling dynamic regulation is executed by the four-order joint control mechanism, which is specifically divided into steps 501, intervention point triggering; Step 502, cooling mode decision; Step 503, running state maintenance; Step 504, energy saving degradation judgment.

[0169] Further, the step 501 monitors the battery pack temperature When detecting , send start instruction to the cooling system, instruction transmission delay 50ms; Synchronous reading of the real-time slope of the predicted temperature change curve .

[0170] The step 502 executes the cooling power level hierarchical strategy based on the real-time slope k of the predicted temperature change curve:

[0171] If (low growth interval), enter low power mode, start fan cooling array, power consumption 300W;

[0172] If (medium growth interval), enter medium power mode, start semiconductor refrigeration piece group, power consumption 1.5kW;

[0173] If (high growth interval), enter high power mode, activate liquid cooling circulating pump and semiconductor refrigeration linkage, power consumption 3.5kW.

[0174] The step 503 enters the high power consumption mode, and when the slope decreases to the middle growth interval, the high power consumption operation is maintained for a fixed time length , the fixed time length According to the battery thermal inertia, the protection time length is set, and after the countdown is over, the medium power consumption mode is switched to.

[0175] The step 504 continuously monitors the temperature difference When the temperature difference (safety margin) and the actual continuous stable time length (stable time length), if the current is high / medium power consumption mode, gradually degrade to low power consumption mode.

[0176] In one specific embodiment, the step 50 process is executed in the case of a certain electric sports car driving on a track.

[0177] In the step 501 intervention point triggering implementation process, the real-time temperature reaches the intervention point , and the cooling start instruction is immediately sent.

[0178] In the step 502 cooling mode decision implementation process, the real-time slope =3.1℃ / min, because (calibration value), the high power consumption mode is triggered, the liquid cooling pump runs at full speed, and the semiconductor refrigeration piece is fully loaded.

[0179] In the step 503 running state maintenance implementation process, after 3 minutes, the slope decreases to =1.8℃ / min (entering the middle growth interval), the fixed time length =45 seconds countdown is started, the high power operation is maintained, and after the countdown is over, the medium power consumption mode is switched to, the liquid cooling pump is turned off, and the semiconductor refrigeration is reduced to 70% power.

[0180] In the step 504 energy-saving degradation judgment implementation process, when the temperature difference and lasts for 120 seconds, the low power consumption mode is switched to, and only the fan operation is retained.

[0181] In the specific implementation process, attention also needs to be paid to the mode switching safety guarantee, the delay time length dynamic calibration, the energy-saving degradation robustness design, and the fault tolerance mechanism.

[0182] The mode switching safety guarantee:

[0183] The power consumption start constraint is performed, and when the slope , the liquid cooling pump is pre-started to eliminate the hydraulic delay;

[0184] The degradation speed limit is performed, and the medium / low power consumption mode switching needs to be through 30 seconds of slope power reduction ), prevent temperature rebound;

[0185] Ensure communication redundancy, control instructions are transmitted through CAN bus and Ethernet dual channels, packet loss rate is less than 0.001%.

[0186] The delay duration is dynamically calibrated, including:

[0187] Carry out thermal inertia modeling, and protect the duration ( Cp is the specific heat capacity, m is the mass, T is the allowable temperature rise, P is the effective refrigeration power of the cooling system);

[0188] Carry out adaptive adjustment, when the battery is aging (SOH < 85%), the protection duration is Extended by 20%; when the ambient temperature is greater than 40℃, the protection duration is Shortened by 15%;

[0189] Carry out boundary protection, and the protection duration is The maximum value does not exceed 30% of the thermal runaway time constant of the battery.

[0190] The energy-saving degradation robustness design includes:

[0191] Carry out safety margin calibration, Increase with the decrease of SOH ( );

[0192] Carry out stable duration constraint, According to the ambient temperature setting (120 seconds at 25℃, shortened to 60 seconds at 40℃);

[0193] Carry out abnormal lock, if the slope breaks through twice within 10 minutes after degradation , forcibly lock the current mode for 30 minutes.

[0194] The fault tolerance mechanism includes:

[0195] When the prediction module fails, the slope fails to degrade, and switches to a simplified model based on current (I is the current);

[0196] Adopt three-way temperature sensor voting mechanism to ensure temperature monitoring redundancy, and take the median value when the deviation is greater than 1℃;

[0197] When the single cell temperature difference is greater than 5℃ or the voltage drops by more than 10%, trigger emergency fuse, and directly start the highest cooling regardless of the mode.

[0198] This invention achieves a fundamental breakthrough in battery thermal safety through a dynamic thermal management system. Its core advantage lies in eliminating the temperature lag risk of traditional fixed threshold mechanisms, transforming passive response into active defense. Based on a dual dynamic compensation mechanism of ambient temperature and battery aging state, it establishes precise and adaptive safety boundaries for different operating conditions, effectively solving the protection failure problem caused by high-temperature environments and battery degradation. Through predictive intervention points and slope-responsive graded cooling strategies, it initiates optimized heat dissipation measures before the temperature reaches the critical point, not only completely avoiding battery exposure to dangerous high-temperature environments and significantly suppressing the erosion of battery life by irreversible side reactions, but also achieving intelligent matching of cooling energy consumption. Combined with online calibration of predictive models and multi-level fault-tolerant design, the system maintains high-precision decision-making and robust operation throughout its entire life cycle, significantly reducing maintenance requirements. Ultimately, it achieves leapfrog progress simultaneously in four dimensions: zero overshoot temperature control, battery life extension, energy efficiency improvement, and system reliability, providing an inherently safe solution for new energy vehicles in all weather and all scenarios.

[0199] Furthermore, the big data-based new energy vehicle battery thermal management system provided by this invention will be described below. The big data-based new energy vehicle battery thermal management system described below can be referred to in correspondence with the big data-based new energy vehicle battery thermal management method described above. Optionally, referencing... Figure 2 , Figure 2 This is a schematic diagram of the structure of the new energy vehicle battery thermal management system based on big data provided by the present invention. The new energy vehicle battery thermal management system based on big data includes...

[0200] The data acquisition and retrieval module 210 collects temperature distribution data, charging and discharging current and voltage data, ambient temperature and humidity data and vehicle driving condition data of each individual cell in the battery pack in real time through a distributed sensor array, and obtains real-time data stream. Based on the current spatiotemporal characteristic parameters, it retrieves historical temperature change curves under similar scenarios from the historical database in the cloud.

[0201] The temperature prediction and slope generation module 220 inputs the real-time data stream and historical temperature change curves into a pre-trained time series prediction model, and outputs the predicted temperature change curve within a future set time window through multi-source data fusion processing, and calculates the real-time temperature rise slope based on the predicted temperature change curve.

[0202] The dynamic safety threshold generation module 230 obtains an environmental comprehensive compensation amount based on the negative compensation effect of ambient temperature on the basic safety threshold and the nonlinear decay effect of battery health status on the basic safety threshold. The environmental comprehensive compensation amount increases monotonically with the increase of ambient temperature and accelerates with the increase of battery aging. The dynamic safety threshold is obtained by subtracting the environmental comprehensive compensation amount from the basic safety threshold.

[0203] The early intervention point decision module 240 determines a dynamic temperature compensation amount through a preset slope grading mechanism based on the real-time temperature rise slope, the dynamic temperature compensation amount is increased step by step with the increase of the slope, the dynamic safety threshold is reduced by the dynamic temperature compensation amount, and an early intervention temperature point is obtained;

[0204] The staged cooling execution module 250 starts the staged cooling system when the battery pack temperature reaches the early intervention temperature point, and dynamically switches the cooling power level according to the growth interval of the real-time temperature rise slope, wherein the cooling intensity is positively correlated with the slope.

[0205] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course, can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method described in each embodiment or some parts of the embodiment.

[0206] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A big data-based new energy vehicle battery thermal management method, characterized in that, The application relates to a battery pack temperature early intervention method based on real-time temperature prediction and dynamic compensation. Real-time data flow is obtained by collecting temperature distribution data, charging and discharging current and voltage data, environment temperature and humidity data and vehicle driving condition data of each single battery cell in a battery pack through a distributed sensor array, and a historical temperature change curve under a similar scene is searched from a cloud historical database based on current space-time characteristic parameters; The real-time data flow and the historical temperature change curve are input into a pre-trained time sequence prediction model, a future set time window prediction temperature change curve is output through multi-source data fusion processing, and a real-time temperature rising slope is calculated based on the prediction temperature change curve; A basic safety threshold is negatively compensated by an environment temperature, and the basic safety threshold is nonlinearly attenuated by a battery health state, so that an environment comprehensive compensation amount is obtained, the environment comprehensive compensation amount monotonously increases with the increase of the environment temperature, and the environment comprehensive compensation amount accelerates the growth with the increase of the battery aging degree; the basic safety threshold is subtracted by the environment comprehensive compensation amount, so that a dynamic safety threshold is obtained; A dynamic temperature compensation amount is determined through a preset slope grading mechanism based on the real-time temperature rising slope, a critical slope of the slope grading mechanism is calibrated according to a first mutation point of a battery material side reaction rate and a boiling starting point of electrolyte, and the critical slope is divided into three growth intervals, namely, a low growth interval, a middle growth interval and a high growth interval; the dynamic temperature compensation amount is stepwisely increased with the increase of the slope; the first fixed compensation amount corresponds to the low growth interval, the second fixed compensation amount greater than the first fixed amount corresponds to the middle growth interval, and the third fixed compensation amount greater than the second fixed amount corresponds to the high growth interval; the dynamic safety threshold is subtracted by the dynamic temperature compensation amount, so that an early intervention temperature point is obtained; When the battery pack temperature reaches the early intervention temperature point, a grading cooling system is started, and the cooling power level is dynamically switched according to the growth interval of the real-time temperature rising slope, wherein the cooling intensity is positively correlated with the slope.

2. The big data-based new energy vehicle battery thermal management method of claim 1, wherein, The segmented linear compensation model is established according to the negative compensation effect of the environment temperature on the basic safety threshold, and the segmented linear compensation model comprises the following steps: When the environment temperature is lower than or equal to a reference temperature, the compensation is not activated; When the environment temperature is in a first high-temperature interval, a first-level compensation amount proportional to the temperature rising amplitude is generated; When the environment temperature enters a second high-temperature interval, a second-level compensation amount greater than the first-level compensation amount is generated; The reference temperature is set according to a battery optimal working temperature range, and boundary values of the first high-temperature interval and the second high-temperature interval are calibrated according to a critical environment temperature of a battery side reaction rate mutation. 3.The big data based new energy vehicle battery thermal management method of claim 1, wherein, The compensation growth model associated with the battery health state is constructed according to the nonlinear attenuation effect of the battery health state on the basic safety threshold, and the compensation growth model comprises the following steps: When the battery health state is higher than a first health threshold, the aging compensation is not activated; When the battery health state is between the first health threshold and a second health threshold, the compensation amount is linearly increased with the decrease of the health state; When the battery health state is lower than the second health threshold, the compensation amount is exponentially increased with the decrease of the health state; The first health threshold is set according to a critical point of first accelerated attenuation of battery capacity, and the second health threshold is calibrated according to a critical point of significant deterioration of battery thermal stability. 4.The big data based new energy vehicle battery thermal management method of claim 1, wherein, The dynamic temperature compensation amount is determined through the preset slope grading mechanism, and the dynamic temperature compensation amount comprises the following steps: a low-growth interval, in which the absolute value of the slope is less than a first critical slope, corresponding to a normal temperature rise stage of the battery, the first critical slope being calibrated according to a temperature change rate at which a first mutation of a battery material side reaction rate occurs; a medium-growth interval, in which the absolute value of the slope is between the first critical slope and a second critical slope, corresponding to a side reaction chain acceleration stage, the second critical slope being calibrated according to a temperature rise rate at which a boiling starting point of an electrolyte occurs; a high-growth interval, in which the absolute value of the slope is greater than the second critical slope, corresponding to a thermal runaway risk stage.

5. The big data-based new energy vehicle battery thermal management method of claim 4, wherein, The mapping relationship between the slope grading mechanism and the dynamic temperature compensation quantity includes: a first fixed value of the dynamic temperature compensation quantity is mapped to the low-growth interval; a second fixed value of the dynamic temperature compensation quantity greater than the first fixed value of the dynamic temperature compensation quantity is mapped to the medium-growth interval; a third fixed value of the dynamic temperature compensation quantity greater than the second fixed value of the dynamic temperature compensation quantity is mapped to the high-growth interval; when it is detected that the slope change rate exceeds a preset acceleration threshold, a buffer dynamic temperature compensation quantity is added to the dynamic temperature compensation quantity corresponding to the fixed value, the acceleration threshold being calibrated according to a battery temperature rise characteristic in a vehicle rapid acceleration working condition. 6.The big data based new energy vehicle battery thermal management method of claim 1, wherein, The dynamic switching of the cooling power level according to the growth interval in which the real-time temperature rise slope is located includes: the highest cooling power is immediately started when the high-growth interval is entered; after the high-growth interval is exited, the highest cooling power is maintained for a set protection time and then downgraded; when the low-growth interval is entered and a stable duration exceeds the set protection time, the high-power cooling device is turned off; when a difference between the real-time temperature and a dynamic safety threshold exceeds a safety margin, the cooling power is triggered to be downgraded to optimize energy consumption; the protection time is set according to a battery thermal inertia time constant, and the safety margin is determined according to a system temperature control accuracy requirement. 7.The big data based new energy vehicle battery thermal management method of claim 1, wherein, The method further includes a safety redundancy control mechanism, when it is detected that a temperature difference between single battery cells exceeds a safety tolerance, a battery internal resistance mutation rate exceeds a critical risk threshold, or an environmental temperature exceeds a system high-temperature warning line and a battery health state is lower than an aging risk threshold, the highest cooling power is directly started, the safety tolerance, the critical risk threshold, and the high-temperature warning line are all calibrated according to battery thermal failure boundary experimental data.

8. A big data based new energy vehicle battery thermal management system implementing the method of any one of claims 1-7, characterized in that, The method includes the following modules: a data acquisition and retrieval module, which acquires temperature distribution data of each single battery cell in a battery pack, charging and discharging current and voltage data, environmental temperature and humidity data, and vehicle driving working condition data in real time through a distributed sensor array, obtains a real-time data stream, and retrieves a historical temperature change curve in a similar scenario based on a current spatiotemporal characteristic parameter from a cloud historical database; a temperature prediction and slope generation module, which inputs the real-time data stream and the historical temperature change curve into a pre-trained time series prediction model, processes multiple source data through fusion, outputs a predicted temperature change curve in a future set time window, and calculates a real-time temperature rise slope based on the predicted temperature change curve; a temperature rise slope calculation module, which calculates a real-time temperature rise slope based on a predicted temperature change curve output by the temperature prediction and slope generation module; The dynamic safety threshold generation module obtains an environment comprehensive compensation amount according to a negative compensation effect of the ambient temperature on the basic safety threshold and a nonlinear attenuation effect of the battery health state on the basic safety threshold, the environment comprehensive compensation amount monotonically increases with the increase of the ambient temperature, and grows faster with the aggravation of the battery aging degree, and the basic safety threshold is subtracted by the environment comprehensive compensation amount to obtain a dynamic safety threshold; The early intervention point decision module determines a dynamic temperature compensation amount through a preset slope grading mechanism based on the real-time temperature rising slope, the dynamic temperature compensation amount increases in steps with the increase of the slope, and the dynamic safety threshold is subtracted by the dynamic temperature compensation amount to obtain an early intervention temperature point; The hierarchical cooling execution module starts the hierarchical cooling system when the battery pack temperature reaches the early intervention temperature point, and dynamically switches the cooling power level according to the growth interval of the real-time temperature rising slope, wherein the cooling strength is positively correlated with the slope.

Images